IoT- Enabled Firmness Grades of Tomato in Cold Supply Chain Using Fusion of Whale Optimization Algorithm and Extreme Learning Machine

Abstract

The firmness of tomatoes is a considerable parameter for the evaluation of harvest time, shelf life, and ripeness. The firmness of tomatoes provides guidance in the distribution and transportation of tomatoes. In the post harvest procedure, the tomato starts losing its firmness and transforming into a rotten state during transportation in the supply chain due to variations in environmental conditions. The cold supply chain for the transportation of tomatoes reduces the loss and maintains the quality of the tomatoes by controlling the environmental conditions. The monitoring of the cold supply chain is crucial for maintaining the quality of tomatoes and overcoming the effect of ambient temperature on tomatoes during logistics. In this study, an IoT and Whale Optimization Algorithm based temperature prediction system for the cold supply chain is presented. The ambient and tomato's temperatures were collected, as well the stable temperature under the variation conditions computed with the Whale Optimization Algorithm for performance improvement. The Extreme Learning Machine of Artificial Intelligence was applied for the predictions. The performance evaluation is done by using precision, recall, and f-measure accuracy metrics. The results of the study show the outstanding performance of the proposed approach rather than the Decision Tree, Linear Model, Naïve Bays, Random Forest, and Support Vector Machine models.